Ai ml api MCP integration
Compares model pricing and limits, creates assistants and threads, drives runs and submits tool outputs, and checks on batch and video jobs.
30actions available
Three actions you can hand over today
Every action runs live through MCP. Nothing to build, nothing to maintain.
Create message
Lyro adds a response to an ongoing conversation thread, keeping the customer dialog flowing. The message gets logged for full conversation history and context preservation.
Create thread
Lyro starts a dedicated conversation channel for each customer inquiry, organizing interactions from first message to resolution. This keeps separate issues from tangling together.
Text chat completion
Lyro generates an AI response by submitting a query to an LLM, returning a complete answer ready to send. This powers intelligent, contextual replies mid-conversation.
How businesses use Ai ml api + Lyro
Each card is one request a support team gets, and the Ai ml api actions Lyro runs to close it.
Pick a model on cost, not on habit
Lyro lists what the account can call and pulls each model's pricing, features, and context limits alongside the current billing balance, so the choice is made against real numbers rather than a default.
List ModelsList Models With DetailsGet Billing BalanceStand up an assistant and its conversation
Lyro creates the assistant with its model and instructions, opens the thread it will work in, and adds the first message, so a new assistant is ready to run in one exchange.
Create AssistantCreate ThreadCreate MessageDrive a run to completion, including its tool calls
Lyro starts the run, hands back results when it pauses waiting on a tool, and reads the step trail to see where it got to, so a stalled run is diagnosed instead of retried blindly.
Create RunSubmit Tool OutputsList Run StepsCheck on work that finishes later
Lyro reads the status of batch processing jobs and fetches Luma video generations by ID once they complete, so long-running work is collected on a later turn rather than blocked on.
List BatchesGet Luma GenerationList Luma AI Generations
How it works
Get started in 3 steps
Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Lyro reads the Ai ml api actions it has and picks the ones a request needs.
- 01
Connect Ai ml api
Authorize the Ai ml api account your team already uses — one consent screen, no API keys, no mapping tables. Lyro can only do what you granted that account, and you can disconnect it at any time.
- 02
Tell your agent what you need
Describe the job the way you would hand it to a teammate. Lyro maps it to the Ai ml api actions that close it and chains as many as the request needs.
- 03
Watch it work
The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.
Get started free
Everything else about Ai ml api
Setup, permissions, and the limits of what Lyro can do inside Ai ml api.
Yes. List Models With Details returns pricing, features, and context limits next to each model, which is the difference between choosing a model deliberately and discovering its cost on an invoice. Get Billing Balance reports what the account has left, so both halves of that decision are available in the same conversation.
Every action available in Ai ml api
All 30 actions your agent can call on Ai ml api, straight from the live MCP connection.
Cancel run
Cancel a run that is currently in progress.
Create assistant
Create an AI assistant with configurable model, instructions, and tools.
Create message
Create a new message in a thread.
Create run
Create a run that executes an assistant on a thread.
Create thread
Create a new thread for conversation with an assistant.
Delete assistant
Delete an assistant by ID.
Delete message
Delete a specific message from a thread.
Delete thread
Delete a thread by its ID.
Get assistant
Retrieve details of a specific assistant by ID.
Get billing balance
Retrieve the current billing balance for the account.
Get luma generation
Fetch Luma AI video generation results by generation IDs.
Get message
Retrieve information about a specific message by its ID.
Get response by ID
Retrieve a previously generated model response by its unique ID.
Get run
Retrieve a specific run by ID from a thread.
Get run step
Retrieve a specific run step by its ID within a thread and run.
Get thread
Retrieve information about a specific thread by ID.
List assistants
List all assistants associated with the account.
List batches
Get the status or results of a batch processing job.
List luma AI generations
Fetch user's Luma AI video generations.
List thread messages
Retrieve a list of messages from a specific thread.
List models
List all available AI models from the AI/ML API.
List models with details
List all available AI/ML models with detailed information including pricing, features, and capabilities.
List runs
List all runs for a specific thread.
List run steps
List the steps in a run.
Submit tool outputs
Submit tool outputs for a run that requires action.
Text chat completion
Generate text completions or chat responses using a specified LLM model.
Update assistant
Modify an existing assistant's properties including name, instructions, model, and tools.
Update message
Modify metadata for a specific message in a thread.
Update run
Update a run's metadata with key-value pairs.
Update thread
Update thread metadata and tool resources in the AI/ML API.
The tools Ai ml api sits next to
Same connection, same setup. Pick the next one your team already uses.
Api labz
Searches Trello cards semantically, lists the tables in an Airtable base, validates an IBAN, and pushes a prepared deal record in.
Datarobot
Reports deployment accuracy and drift, starts Autopilot runs, queues batch predictions, and keeps datasets linked to the right use case.
Google cloud vision
Runs OCR and image annotation over pictures and PDFs, builds the Product Search catalogue, and polls long-running batch operations.
Metaphor
Fetches the parsed text and metadata for Metaphor documents by ID, several at a time, turning a set of result IDs into readable content.
Rev AI
Submits recordings for transcription, returns transcripts and SRT or VTT captions, and maintains the custom vocabulary behind accuracy.
Tisane
Detects the language of a message, flags abuse types and sentiment, scores text similarity, and paraphrases or translates a passage.
Ready to connect Ai ml api?
Authorize the account and your agent has all 30 actions from the first conversation.